INDEX

Explanations

These

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sno

-0.28

è´¨éĩıåĴĮ

-0.28

ussen

-0.27

UW

-0.26

wl

-0.25

==$

-0.25

udder

-0.25

ä¸įä¿¡

-0.25

 spheres

-0.25

successfully

-0.24

POSITIVE LOGITS

çĻĸ

0.31

ialis

0.31

Ne

0.29

Ne

0.26

htag

0.25

-floating

0.25

åı£åĳ³

0.25

 fifth

0.25

STYLE

0.24

.Touch

0.24

Activations Density 0.006%

These

No Comments

No Known Activations